An efficient hybrid technique for energy management system with renewable energy system and energy storage system in smart grid

Abstract

This manuscript proposes a hybrid technique for an energy management system (EMS) with a renewable energy system and energy storage system using the smart micro grid. This work's novelty liesin the integration of Flying Foxes Optimization (FFO) algorithm and Deep Attention Dilated Residual Convolutional Neural Network (DADRCNN). Unlike existing methods, the FFO-DADRCNN method effectively leverages both optimization and predictive modelling capabilities to enhance grid stability, efficiency, and load prediction accuracy. The main goals of the proposed approach are to increase grid stability and efficiency, decrease micro grid system costs, and increase load prediction accuracy. The micro grid system incorporates PV, an energy storage system, wind turbine and load demand. To regulate the micro grid system and estimate load utilizing the DADRCNN most effectively, the proposed FFO technique is used. The proposed method's performance is evaluated using the MATLAB platform and compared with existing approaches, including Giza Pyramids Construction, Heap-based optimizer, and Nomadic People Optimizer. The proposed technique shows better outcomes when compared to other methods. Compared to other methods currently available, our proposed approach boasts an impressive 98 % efficiency rate and comes at a low operating cost of $1840.